Author
Listed:
- M. Muthumanjula
- Ramasubramanian Bhoopalan
Abstract
Medical diagnosis, notably concerning tumors, has been transformed by artificial intelligence as well as deep neural network. White blood cell identification, in particular, necessitates effective diagnosis and therapy. White Blood Cell Cancer (WBCC) comes in a variety of forms. Acute Leukemia Lymphocytes (ALL), Acute Myeloma Lymphocytes (AML), Chronic Leukemia Lymphocytes (CLL), and Chronic Myeloma Lymphocytes (CML) are white blood cell cancers for which detection is time-consuming procedure, vulnerable to sentient as well as equipment blunders. Despite just a comprehensive review with a competent examiner, it can be hard to render a precise conclusive determination in some cases. Conversely, Computer-Aided Diagnosis (CAD) may assist in lessening the number of inaccuracies as well as duration spent in diagnosing WBCC. Though deep learning is widely regarded as the most advanced method for detecting WBCCs, the richness of the retrieved attributes employed in developing the pixel-wise categorization algorithms has a substantial relationship with the efficiency of WBCC identification. The investigation of the various phases of alterations related with WBC concentrations and characteristics is crucial to CAD. Leveraging image handling plus deep learning technologies, a novel fusion characteristic retrieval technique has been created in this research. The suggested approach is divided into two parts: 1) The CMYK-moment localization approach is applied to define the Region of Interest (ROI) and 2) A CNN dependent characteristic blend strategy is utilized to obtain deep learning characteristics. The relevance of the retrieved characteristics is assessed via a variety of categorization techniques. The suggested component collection approach versus different attributes retrieval techniques is tested with an exogenous resource. With all the predictors, the suggested methodology exhibits good effectiveness, adaptability, including consistency, exhibiting aggregate categorization accuracies of 97.57 percent and 96.41 percent, correspondingly, utilizing the main as well as auxiliary samples. This approach has provided a novel option for enhancing CLL identification that may result towards a more accurate identification of malignancies.
Suggested Citation
Handle:
RePEc:gvu:iroism:v:4:y:2022:i:1:id:955
DOI: 10.36548/jismac.2022.1.006
Download full text from publisher
Corrections
All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gvu:iroism:v:4:y:2022:i:1:id:955. See general information about how to correct material in RePEc.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
We have no bibliographic references for this item. You can help adding them by using this form .
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Journal Manager (email available below). General contact details of provider: https://irojournals.com/iroismac .
Please note that corrections may take a couple of weeks to filter through
the various RePEc services.